© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 23543
    Prev
    Next
    INDEX
    Explanations

    the word "time" along with verbs indicating an action or situation that is repeated in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "every time."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ye
    -0.76
    agar
    -0.70
    ajor
    -0.68
    ryu
    -0.67
    XT
    -0.67
    ourt
    -0.66
    ipation
    -0.66
    otto
    -0.66
    ersive
    -0.65
    yright
    -0.65
    POSITIVE LOGITS
    soever
    0.76
     someone
    0.75
    frames
    0.73
     somebody
    0.73
     frame
    0.69
    frame
    0.68
     lapse
    0.67
     else
    0.64
    click
    0.63
     clicking
    0.63
    Activations Density 0.027%

    No Known Activations